Deep Learning-Based Constellation Optimization for Physical Network Coding in Two-Way Relay Networks

Abstract

This paper studies a new application of deep learning (DL) for optimizing constellations in two-way relaying with physical-layer network coding (PNC), where deep neural network (DNN)-based modulation and demodulation are employed at each terminal and relay node. We train DNNs such that the cross entropy loss is directly minimized, and thus it maximizes the likelihood, rather than considering the Euclidean distance of the constellations. The proposed scheme can be extended to higher level constellations with slight modification of the DNN structure. Simulation results demonstrate a significant performance gain in terms of the achievable sum rate over conventional relaying schemes. Furthermore, since our DNN demodulator directly outputs bit-wise probabilities, it is straightforward to concatenate with soft-decision channel decoding.

End-to-End Learning-Based Framework for Amplify-and-Forward Relay Networks

“…On the other hand, the bit-wise AE framework, takes k bits as input and output of the AE, while the AE is optimized by minimizing the binary CE loss. The bit-wise AE framework has been investigated for P2P networks in [17], and for AF and DF relay networks in [18] and [19], respectively. Although the bit-wise AEs seem like a trivial modification of the symbol-wise AEs, but by providing the bit-wise AE's input and output in the form of bits, we obtain automatic bit-labeling.…”

“…Thus, bit-wise AE has appeared as a novel research direction to obtain block codes for short block lengths in a P2P network. Although the authors in [18] focussed on bit-wise AE-based 2-dimensional modulation design with the achievable-sumrate analysis for the AF relay networks, the bit-wise AEbased coded-modulation design has never been studied in the literature for AF relay networks, but also its BER analysis.…”

A Survey about Deep Learning for Constellation Design in Communications

“…The points with a greater occurrence are placed in the center, and this occurrence is greater for lower SNRs. In [15], Matsumine et. al.…”

Update-Based Machine Learning Classification of Hierarchical Symbols in a Slowly Varying Two-Way Relay Channel

“…In [8,9], a deep learning approach to jointly optimize the whole wireless communication chain was proposed, and this approach was successfully tested in an over-the-air transmission. Similar to this, in the context of WPLNC, the authors in [10] addressed parts of the network chain as individual deep neural networks, divided into the source modulator, a relay node, and the demodulator. Attention attracted also the approach of modulation classification in [12], where it was interpreted as an image classification problem.…”

“…The problems of stochastic inference interpreted as ML tasks have attracted considerable attention in the field of physical layer communication [7][8][9][10]. The classical mathematical formulations of detection, estimation, and signal processing algorithms usually require a precise analytical knowledge of the system and observation model and usually lead to provable optimal closed-form results.…”